Prediction of candidates for spinal neuromodulation
AssigneeRelievant Medsystems, Inc.
InventorsBrian W. DONOVAN, Ray M. BAKER, Samit PATEL
Life of this patent
Estimating the term…
Abstract
Described herein are various implementations of systems and methods for determining likelihood of a patient favorably responding to a neuromodulation procedure based on a quantitative or objective score or determination based on a plurality of indicators of pain (e.g., chronic low back pain stemming from one or more vertebral bodies or vertebral endplates of a patient). The systems and methods may involve application of artificial intelligence techniques (e.g., trained algorithms, machine learning or deep learning algorithms, and/or trained neural networks).
Claims20
A computer-implemented method of predicting treatment candidacy for basivertebral nerve ablation, the method comprising:
- receiving one or more digital images of at least a portion of a spine of a subject;
- pre-processing the one or more digital images to generate one or more pre-processed digital images;
- applying an outcome-trained model to the one or more pre-processed digital images to identify one or more pre-Modic change characteristics associated with a vertebral body or vertebral endplate of the subject, wherein the one or more pre-Modic change characteristics comprise imaging characteristics that provide initial indications or precursors of potential Modic changes before formal characterization of the imaging characteristics as Modic changes;
- determining, using the outcome-trained model, a treatment-response score indicative of a likelihood that the subject would respond favorably to basivertebral nerve ablation based on the identified one or more pre-Modic change characteristics;
- and
- outputting an indication of treatment candidacy for basivertebral nerve ablation based on the treatment-response score.
A computer-implemented method of generating an outcome-trained model for predicting treatment candidacy for basivertebral nerve ablation, the method comprising:
- receiving a first set of training images comprising images of at least a portion of spines of subjects who previously received basivertebral nerve ablation;
- associating the first set of training images with outcome annotations indicating treatment success or treatment failure following basivertebral nerve ablation;
- pre-processing the first set of training images to generate a normalized training image set;
- training a model, using the normalized training image set and the outcome annotations, to identify one or more pre-Modic change characteristics associated with treatment response to basivertebral nerve ablation;
- and
- generating the outcome-trained model for application to one or more subject images to determine a treatment-response score indicative of a likelihood that a particular subject would respond favorably to basivertebral nerve ablation.
A system for identifying candidate vertebral bodies for basivertebral nerve ablation, the system comprising:
- at least one memory device storing computer-executable instructions;
- and
- at least one processor configured to execute the computer-executable instructions to:
- receive one or more digital images of at least a portion of a spine of a subject;
- analyze the one or more digital images to identify one or more precursor characteristics associated with a vertebral body or vertebral endplate of the subject before formal characterization of the one or more precursor characteristics as Modic changes;
- determine, based on the identified one or more precursor characteristics, a risk score indicative of a likelihood that the vertebral body or vertebral endplate is associated with developing or worsening vertebrogenic back pain;
- and
- output an indication identifying the vertebral body as a candidate vertebral body for basivertebral nerve ablation.
Dependencies are inferred from the claim text.